Training in progress, epoch 0
Browse files- config.json +101 -0
- model.safetensors +3 -0
- preprocessor_config.json +13 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "MIT/ast-finetuned-audioset-10-10-0.4593",
|
3 |
+
"architectures": [
|
4 |
+
"ASTForAudioClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"frequency_stride": 10,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.0,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": 0,
|
13 |
+
"1": 1,
|
14 |
+
"10": 10,
|
15 |
+
"11": 11,
|
16 |
+
"12": 12,
|
17 |
+
"13": 13,
|
18 |
+
"14": 14,
|
19 |
+
"15": 15,
|
20 |
+
"16": 16,
|
21 |
+
"17": 17,
|
22 |
+
"18": 18,
|
23 |
+
"19": 19,
|
24 |
+
"2": 2,
|
25 |
+
"20": 20,
|
26 |
+
"21": 21,
|
27 |
+
"22": 22,
|
28 |
+
"23": 23,
|
29 |
+
"24": 24,
|
30 |
+
"25": 25,
|
31 |
+
"26": 26,
|
32 |
+
"27": 27,
|
33 |
+
"28": 28,
|
34 |
+
"29": 29,
|
35 |
+
"3": 3,
|
36 |
+
"30": 30,
|
37 |
+
"31": 31,
|
38 |
+
"32": 32,
|
39 |
+
"33": 33,
|
40 |
+
"34": 34,
|
41 |
+
"35": 35,
|
42 |
+
"4": 4,
|
43 |
+
"5": 5,
|
44 |
+
"6": 6,
|
45 |
+
"7": 7,
|
46 |
+
"8": 8,
|
47 |
+
"9": 9
|
48 |
+
},
|
49 |
+
"initializer_range": 0.02,
|
50 |
+
"intermediate_size": 3072,
|
51 |
+
"label2id": {
|
52 |
+
"0": "0",
|
53 |
+
"1": "1",
|
54 |
+
"2": "2",
|
55 |
+
"3": "3",
|
56 |
+
"4": "4",
|
57 |
+
"5": "5",
|
58 |
+
"6": "6",
|
59 |
+
"7": "7",
|
60 |
+
"8": "8",
|
61 |
+
"9": "9",
|
62 |
+
"10": "10",
|
63 |
+
"11": "11",
|
64 |
+
"12": "12",
|
65 |
+
"13": "13",
|
66 |
+
"14": "14",
|
67 |
+
"15": "15",
|
68 |
+
"16": "16",
|
69 |
+
"17": "17",
|
70 |
+
"18": "18",
|
71 |
+
"19": "19",
|
72 |
+
"20": "20",
|
73 |
+
"21": "21",
|
74 |
+
"22": "22",
|
75 |
+
"23": "23",
|
76 |
+
"24": "24",
|
77 |
+
"25": "25",
|
78 |
+
"26": "26",
|
79 |
+
"27": "27",
|
80 |
+
"28": "28",
|
81 |
+
"29": "29",
|
82 |
+
"30": "30",
|
83 |
+
"31": "31",
|
84 |
+
"32": "32",
|
85 |
+
"33": "33",
|
86 |
+
"34": "34",
|
87 |
+
"35": "35"
|
88 |
+
},
|
89 |
+
"layer_norm_eps": 1e-12,
|
90 |
+
"max_length": 1024,
|
91 |
+
"model_type": "audio-spectrogram-transformer",
|
92 |
+
"num_attention_heads": 12,
|
93 |
+
"num_hidden_layers": 12,
|
94 |
+
"num_mel_bins": 128,
|
95 |
+
"patch_size": 16,
|
96 |
+
"problem_type": "single_label_classification",
|
97 |
+
"qkv_bias": true,
|
98 |
+
"time_stride": 10,
|
99 |
+
"torch_dtype": "float32",
|
100 |
+
"transformers_version": "4.35.0"
|
101 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66cb7d935aca1c2a5b9cece80810da9bb3af7c3c8c29cd574e5bbf5850b9baba
|
3 |
+
size 344894632
|
preprocessor_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"feature_extractor_type": "ASTFeatureExtractor",
|
4 |
+
"feature_size": 1,
|
5 |
+
"max_length": 1024,
|
6 |
+
"mean": -4.2677393,
|
7 |
+
"num_mel_bins": 128,
|
8 |
+
"padding_side": "right",
|
9 |
+
"padding_value": 0.0,
|
10 |
+
"return_attention_mask": false,
|
11 |
+
"sampling_rate": 16000,
|
12 |
+
"std": 4.5689974
|
13 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76a7cc14c01efda2ebc9853a87a44d7fdc10944b53b7fff6b6935b1e10275a3b
|
3 |
+
size 4600
|